Search Results for author:
Found 29 papers, 17 papers with code
Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
Rapid and reliable identification of dynamic scene parts, also known as motion segmentation, is a key challenge for mobile sensors.
Event-based Image Deblurring with Dynamic Motion Awareness
Non-uniform image deblurring is a challenging task due to the lack of temporal and textural information in the blurry image itself.
FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots.
Time Lens++: Event-based Frame Interpolation with Parametric Non-linear Flow and Multi-scale Fusion
Recently, video frame interpolation using a combination of frame- and event-based cameras has surpassed traditional image-based methods both in terms of performance and memory efficiency.
Multi-Bracket High Dynamic Range Imaging with Event Cameras
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times.
Time Lens: Event-Based Video Frame Interpolation
However, while these approaches can capture non-linear motions they suffer from ghosting and perform poorly in low-texture regions with few events.
TimeLens: Event-based Video Frame Interpolation
State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames.
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection.
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance.
Exploring Relational Context for Multi-Task Dense Prediction
Our goal is to find the most efficient way to refine each task prediction by capturing cross-task contexts dependent on tasks' relations.
Ranked #86 on
Semantic Segmentation
on NYU Depth v2
Spectral Tensor Train Parameterization of Deep Learning Layers
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context.
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals
To achieve this, we introduce a two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings.
Ranked #3 on
Unsupervised Semantic Segmentation
on ImageNet-S-50
Automated Search for Resource-Efficient Branched Multi-Task Networks
The multi-modal nature of many vision problems calls for neural network architectures that can perform multiple tasks concurrently.
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning).
T-Basis: a Compact Representation for Neural Networks
Each of the tensors in the set is modeled using Tensor Rings, though the concept applies to other Tensor Networks.
SCAN: Learning to Classify Images without Labels
First, a self-supervised task from representation learning is employed to obtain semantically meaningful features.
Ranked #4 on
Image Clustering
on ImageNet-200
Multi-Task Learning for Dense Prediction Tasks: A Survey
In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision, explicitly emphasizing on dense prediction tasks.
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup.
Ranked #7 on
Semantic Segmentation
on UrbanLF
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks.
Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
State-of-the-art approaches for semantic segmentation rely on deep convolutional neural networks trained on fully annotated datasets, that have been shown to be notoriously expensive to collect, both in terms of time and money.
Image Segmentation
Weakly supervised Semantic Segmentation
+1
Branched Multi-Task Networks: Deciding What Layers To Share
In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand.
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
Experimental results on various datasets show that EGSC-IT does not only translate the source image to diverse instances in the target domain, but also preserves the semantic consistency during the process.
Towards End-to-End Lane Detection: an Instance Segmentation Approach
By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation.
Ranked #16 on
Lane Detection
on TuSimple
Error Correction for Dense Semantic Image Labeling
Pixelwise semantic image labeling is an important, yet challenging, task with many applications.
Disentangled Person Image Generation
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information.
Ranked #2 on
Gesture-to-Gesture Translation
on Senz3D
Fast Scene Understanding for Autonomous Driving
Most approaches for instance-aware semantic labeling traditionally focus on accuracy.
What Is Around The Camera?
How much does a single image reveal about the environment it was taken in?
DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
In this paper we are extracting surface reflectance and natural environmental illumination from a reflectance map, i. e. from a single 2D image of a sphere of one material under one illumination.
A Gaussian Process Latent Variable Model for BRDF Inference
Although inferring higher dimensional BRDFs from such modest training is not a trivial problem, our method performs better than state-of-the-art parametric, semi-parametric and non-parametric approaches.
